Data Visualization Tutorial

R Markdown

library(tidyverse)

## ── Attaching packages ────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.3     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.5.0

## ── Conflicts ───────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

surveys_complete <- read_csv("data/surveys_complete.csv")

## Parsed with column specification:
## cols(
##   record_id = col_double(),
##   month = col_double(),
##   day = col_double(),
##   year = col_double(),
##   plot_id = col_double(),
##   species_id = col_character(),
##   sex = col_character(),
##   hindfoot_length = col_double(),
##   weight = col_double(),
##   genus = col_character(),
##   species = col_character(),
##   taxa = col_character(),
##   plot_type = col_character()
## )

ggplot(data = surveys_complete)

ggplot(data = surveys_complete, mapping = aes(x = weight, y = hindfoot_length))

ggplot(data = surveys_complete, aes(x = weight, y = hindfoot_length)) +
  geom_point()

install.packages("hexbin")

## Installing package into '/home/rstudio-user/R/x86_64-pc-linux-gnu-library/4.0'
## (as 'lib' is unspecified)

library("hexbin")

ggplot(data = surveys_complete, aes(x = weight, y = hindfoot_length)) +
    geom_point()

ggplot(data = surveys_complete, aes(x = weight, y = hindfoot_length)) +
    geom_point(alpha = 0.1)

ggplot(data = surveys_complete, mapping = aes(x = weight, y = hindfoot_length)) +
    geom_point(alpha = 0.1, color = "blue")

ggplot(data = surveys_complete, mapping = aes(x = weight, y = hindfoot_length)) +
    geom_point(alpha = 0.1, aes(color = species_id))

ggplot(data = surveys_complete, 
       mapping = aes(x = species_id, y = weight)) +
   geom_point(aes(color = plot_type))

ggplot(data = surveys_complete, mapping = aes(x = species_id, y = weight)) +
    geom_boxplot()

ggplot(data = surveys_complete, mapping = aes(x = species_id, y = weight)) +
    geom_boxplot(alpha = 0) +
    geom_jitter(alpha = 0.3, color = "tomato")

ggplot(data = surveys_complete, mapping = aes(x = species_id, y = weight)) +
    geom_violin() +
  scale_y_log10()

ggplot(data = surveys_complete, mapping = aes(x = species_id, y = hindfoot_length)) +
    geom_violin() +
  scale_y_log10() +
  geom_jitter(alpha = 0.3, color = "tomato")

yearly_counts <- surveys_complete %>%
  count(year, genus)

ggplot(data = yearly_counts, aes(x = year, y = n)) +
     geom_line()

ggplot(data = yearly_counts, aes(x = year, y = n, group = genus)) +
    geom_line()

ggplot(data = yearly_counts, aes(x = year, y = n, color = genus)) +
    geom_line()

yearly_counts_graph <- surveys_complete %>%
    count(year, genus) %>% 
    ggplot(mapping = aes(x = year, y = n, color = genus)) +
    geom_line()

yearly_counts_graph

ggplot(data = yearly_counts, aes(x = year, y = n)) +
    geom_line() +
    facet_wrap(facets = vars(genus))

 yearly_sex_counts <- surveys_complete %>%
                      count(year, genus, sex)

ggplot(data = yearly_sex_counts, mapping = aes(x = year, y = n, color = sex)) +
  geom_line() +
  facet_wrap(facets =  vars(genus))

ggplot(data = yearly_sex_counts, 
       mapping = aes(x = year, y = n, color = sex)) +
  geom_line() +
  facet_grid(rows = vars(sex), cols =  vars(genus))

# One column, facet by rows
ggplot(data = yearly_sex_counts, 
       mapping = aes(x = year, y = n, color = sex)) +
  geom_line() +
  facet_grid(rows = vars(genus))

# One row, facet by column
ggplot(data = yearly_sex_counts, 
       mapping = aes(x = year, y = n, color = sex)) +
  geom_line() +
  facet_grid(cols = vars(genus))

ggplot(data = yearly_sex_counts, 
        mapping = aes(x = year, y = n, color = sex)) +
     geom_line() +
     facet_wrap(vars(genus)) +
     theme_bw()

yearly_weight <- surveys_complete %>%
                group_by(year, species_id) %>%
                 summarize(avg_weight = mean(weight))

## `summarise()` regrouping output by 'year' (override with `.groups` argument)

ggplot(data = yearly_weight, mapping = aes(x=year, y=avg_weight)) +
   geom_line() +
   facet_wrap(vars(species_id)) +
   theme_light()

ggplot(data = yearly_sex_counts, aes(x = year, y = n, color = sex)) +
    geom_line() +
    facet_wrap(vars(genus)) +
    labs(title = "Observed genera through time",
         x = "Year of observation",
         y = "Number of individuals") +
    theme_bw()

ggplot(data = yearly_sex_counts, mapping = aes(x = year, y = n, color = sex)) +
    geom_line() +
    facet_wrap(vars(genus)) +
    labs(title = "Observed genera through time",
        x = "Year of observation",
        y = "Number of individuals") +
    theme_bw() +
    theme(text=element_text(size = 16))

ggplot(data = yearly_sex_counts, mapping = aes(x = year, y = n, color = sex)) +
    geom_line() +
    facet_wrap(vars(genus)) +
    labs(title = "Observed genera through time",
        x = "Year of observation",
        y = "Number of individuals") +
    theme_bw() +
    theme(axis.text.x = element_text(colour = "grey20", size = 12, angle = 90, hjust = 0.5, vjust = 0.5),
                        axis.text.y = element_text(colour = "grey20", size = 12),
                        strip.text = element_text(face = "italic"),
                        text = element_text(size = 16))

grey_theme <- theme(axis.text.x = element_text(colour="grey20", size = 12, 
                                               angle = 90, hjust = 0.5, 
                                               vjust = 0.5),
                    axis.text.y = element_text(colour = "grey20", size = 12),
                    text=element_text(size = 16))

ggplot(surveys_complete, aes(x = species_id, y = hindfoot_length)) +
    geom_boxplot() +
    grey_theme

ggplot(surveys_complete, aes(x = species_id, y = hindfoot_length)) +
    geom_rug() +
    grey_theme